English(EN)Accelerated Mixing Time of Randomized Hamiltonian Monte Carlo
新的HMC算法解决了偏差并加速了采样时间 · 跟踪7个来源
作者PulseAugur 编辑部·[7 个来源]·
研究人员开发了新的方法来解决哈密顿蒙特卡洛（HMC）算法中的偏差并提高效率。一项研究将偏差去局域化的概念扩展到未调整的HMC和欠阻尼Langevin方法，表明有限数量的积分步数可以控制高维分布中的偏差。另一篇论文介绍了随机哈密顿蒙特卡洛（RHMC），该方法通过使用随机积分时间，证明了从对数凹分布采样的加速混合时间保证。第三种方法，驯服随机梯度哈密顿蒙特卡洛（tSGHMC），被提出用于具有超线性增长梯度的优化问题，提供了理论保证，并在实际应用中优于其一阶对应方法。
AI
Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to eliminate the bias. However, this adjustment can significantly…
We show the Randomized Hamiltonian Monte Carlo (RHMC) algorithm has accelerated mixing time guarantees for sampling from log-concave probability distributions. RHMC proceeds by repeatedly simulating the continuous-time Hamiltonian dynamics for some random integration times, and r…
arXiv:2607.14862v1 Announce Type: cross Abstract: In this paper, we propose a novel tamed stochastic gradient Hamiltonian Monte Carlo (tSGHMC) algorithm for sampling and stochastic optimization problems with superlinearly growing stochastic gradients. Under a certain continuity i…
arXiv stat.ML
TIER_1English(EN)·Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed, Jonathan Weare·
arXiv:2607.15208v1 Announce Type: cross Abstract: Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorporated into Hamiltonian Monte Carlo to eliminate th…
In this paper, we propose a novel tamed stochastic gradient Hamiltonian Monte Carlo (tSGHMC) algorithm for sampling and stochastic optimization problems with superlinearly growing stochastic gradients. Under a certain continuity in average condition and a strong convexity conditi…
arXiv stat.ML
TIER_1English(EN)·Siddharth Mitra, Vishwak Srinivasan, Xiuyuan Wang, Andre Wibisono·
arXiv:2607.12902v1 Announce Type: new Abstract: We show the Randomized Hamiltonian Monte Carlo (RHMC) algorithm has accelerated mixing time guarantees for sampling from log-concave probability distributions. RHMC proceeds by repeatedly simulating the continuous-time Hamiltonian d…
We show the Randomized Hamiltonian Monte Carlo (RHMC) algorithm has accelerated mixing time guarantees for sampling from log-concave probability distributions. RHMC proceeds by repeatedly simulating the continuous-time Hamiltonian dynamics for some random integration times, and r…
